首页> 外文会议>International Conference on Graphic and Image Processing >Feature-Fused SSD: Fast Detection for Small Objects
【24h】

Feature-Fused SSD: Fast Detection for Small Objects

机译:功能融合SSD:小对象的快速检测

获取原文

摘要

Small objects detection is a challenging task in computer vision due to its limited resolution and information. In order to solve this problem, the majority of existing methods sacrifice speed for improvement in accuracy. In this paper, we aim to detect small objects at a fast speed, using the best object detector Single Shot Multibox Detector (SSD) with respect to accuracy-vs-speed trade-off as base architecture. We propose a multi-level feature fusion method for introducing contextual information in SSD, in order to improve the accuracy for small objects. In detailed fusion operation, we design two feature fusion modules, concatenation module and element-sum module, different in the way of adding contextual information. Experimental results show that these two fusion modules obtain higher mAP on PASCAL VOC2007 than baseline SSD by 1.6 and 1.7 points respectively, especially with 2-3 points improvement on some small objects categories. The testing speed of them is 43 and 40 FPS respectively, superior to the state of the art Deconvolutional single shot detector (DSSD) by 29.4 and 26.4 FPS.
机译:由于其分辨率和信息有限,小对象检测是计算机愿景中的具有挑战性的任务。为了解决这个问题,大多数现有方法牺牲了准确性提高的速度。在本文中,我们的目标是以快速速度检测小物体,使用最佳对象检测器单次拍摄多射门探测器(SSD)作为基础架构的精度VS速调。我们提出了一种用于在SSD中引入上下文信息的多级特征融合方法,以提高小物体的准确性。在详细的融合操作中,我们设计了两个特征融合模块,级联模块和元素和元素模块,以添加上下文信息的方式不同。实验结果表明,这两个融合模块分别在Pascal Voct2007上获得了更高的地图,而不是基线SSD分别为1.6和1.7分,特别是对某些小物体类别的2-3点改进。它们的测试速度分别为43和40fps,优于现有的解卷积单次检测器(DSSD)29.4和26.4 FPS的状态。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号